Merge pull request #73 from chronicle-app/use-chronicle-core

Use new Chronicle Schema work from chronicle-core

.rubocop.yml

@@ -1,44 +1,2 @@
-AllCops:
-  EnabledByDefault: true
-  TargetRubyVersion: 2.7
-
-Style/FrozenStringLiteralComment:
-  SafeAutoCorrect: true
-
-Style/StringLiterals:
-  Enabled: false
-
-Layout/MultilineAssignmentLayout:
-  Enabled: false
-
-Layout/MultilineMethodCallIndentation:
-  EnforcedStyle: indented
-
-Layout/RedundantLineBreak:
-  Enabled: false
-
-Style/MethodCallWithArgsParentheses:
-  Enabled: false
-
-Style/MethodCalledOnDoEndBlock:
-  Exclude:
-    - 'spec/**/*'
-
-Style/OpenStructUse:
-  Enabled: false
-
-Style/Copyright:
-  Enabled: false
-
-Style/MissingElse:
-  Enabled: false
-
-Style/SymbolArray:
-  EnforcedStyle: brackets
-
-Style/WordArray:
-  EnforcedStyle: brackets
-
-Lint/ConstantResolution:
-  Enabled: false
-
+inherit_gem:
+  chronicle-core: .rubocop.yml

Gemfile

@@ -1,6 +1,6 @@
-source "https://rubygems.org"
+source 'https://rubygems.org'
 
-git_source(:github) {|repo_name| "https://github.com/#{repo_name}" }
+git_source(:github) { |repo_name| "https://github.com/#{repo_name}" }
 
 # Specify your gem's dependencies in chronicle-etl.gemspec
 gemspec

Guardfile

@@ -1,7 +1,7 @@
-guard :rspec, cmd: "bundle exec rspec" do
-  require "guard/rspec/dsl"
+guard :rspec, cmd: 'bundle exec rspec' do
+  require 'guard/rspec/dsl'
 
   watch(%r{^spec/.+_spec\.rb$})
   watch(%r{^lib/(.+)\.rb$})     { |m| "spec/#{m[1]}_spec.rb" }
-  watch('spec/spec_helper.rb')  { "spec" }
+  watch('spec/spec_helper.rb')  { 'spec' }
 end

README.md

@@ -6,14 +6,14 @@
 
 Are you trying to archive your digital history or incorporate it into your own projects? You’ve probably discovered how frustrating it is to get machine-readable access to your own data. While [building a memex](https://hyfen.net/memex/), I learned first-hand what great efforts must be made before you can begin using the data in interesting ways.
 
-If you don’t want to spend all your time writing scrapers, reverse-engineering APIs, or parsing takeout data, this tool is for you! (_If you do enjoy these things, please see the [open issues](https://github.com/chronicle-app/chronicle-etl/issues)._)
+If you don’t want to spend all your time writing scrapers, reverse-engineering APIs, or parsing export data, this tool is for you! (_If you do enjoy these things, please see the [open issues](https://github.com/chronicle-app/chronicle-etl/issues)._)
 
 **`chronicle-etl` is a CLI tool that gives you a unified interface to your personal data.** It uses the ETL pattern to _extract_ data from a source (e.g. your local browser history, a directory of images, goodreads.com reading history), _transform_ it (into a given schema), and _load_ it to a destination (e.g. a CSV file, JSON, external API).
 
 ## What does `chronicle-etl` give you?
 
 - **A CLI tool for working with personal data**. You can monitor progress of exports, manipulate the output, set up recurring jobs, manage credentials, and more.
-- **Plugins for many third-party providers** (see [list](#available-plugins-and-connectors)). This plugin system allows you to access data from dozens of third-party services, all accessible through a common CLI interface.
+- **Plugins for many third-party sources** (see [list](#available-plugins-and-connectors)). This plugin system allows you to access data from dozens of third-party services, all accessible through a common CLI interface.
 - **A common, opinionated schema**: You can normalize different datasets into a single schema so that, for example, all your iMessages and emails are represented in a common schema. (Don’t want to use this schema? `chronicle-etl` always allows you to fall back on working with the raw extraction data.)
 
 ## Chronicle-ETL in action
@@ -58,10 +58,10 @@ $ chronicle-etl --extractor csv --input data.csv --loader table
 
 # Show available plugins and install one
 $ chronicle-etl plugins:list
-$ chronicle-etl plugins:install shell
+$ chronicle-etl plugins:install imessage
 
-# Retrieve shell commands run in the last 5 hours
-$ chronicle-etl -e shell --since 5h
+# Retrieve imessage messages from the last 5 hours
+$ chronicle-etl -e imessage --since 5h
 
 # Get email senders from an .mbox email archive file
 $ chronicle-etl --extractor email:mbox -i sample-email-archive.mbox -t email --fields actor.slug
@@ -80,12 +80,16 @@ Options:
       [--extractor-opts=key:value]       # Extractor options
   -t, [--transformer=NAME]               # Transformer class. Default: null
       [--transformer-opts=key:value]     # Transformer options
-  -l, [--loader=NAME]                    # Loader class. Default: table
+  -l, [--loader=NAME]                    # Loader class. Default: json
       [--loader-opts=key:value]          # Loader options
   -i, [--input=FILENAME]                 # Input filename or directory
       [--since=DATE]                     # Load records SINCE this date (or fuzzy time duration)
       [--until=DATE]                     # Load records UNTIL this date (or fuzzy time duration)
       [--limit=N]                        # Only extract the first LIMIT records
+      [--schema=SCHEMA_NAME]             # Which Schema to transform
+                                         # Possible values: chronicle, activitystream, schemaorg, chronobase
+      [--format=SCHEMA_NAME]              # How to serialize results
+                                          # Possible values: jsonapi, jsonld
   -o, [--output=OUTPUT]                  # Output filename
       [--fields=field1 field2 ...]       # Output only these fields
       [--header-row], [--no-header-row]  # Output the header row of tabular output
@@ -119,7 +123,7 @@ $ chronicle-etl jobs:list
 
 ## Connectors and plugins
 
-Connectors let you work with different data formats or third-party providers.
+Connectors let you work with different data formats or third-party sources.
 
 ### Built-in Connectors
 
@@ -139,13 +143,16 @@ $ chronicle-etl connectors:list
 #### Transformers
 
 - [`null`](https://github.com/chronicle-app/chronicle-etl/blob/main/lib/chronicle/etl/transformers/null_transformer.rb) - (default) Don’t do anything and pass on raw extraction data
+- [`sampler`](https://github.com/chronicle-app/chronicle-etl/blob/main/lib/chronicle/etl/transformers/sampler_transformer.rb) - Sample `percent` records from the extraction
+- [`sort`](https://github.com/chronicle-app/chronicle-etl/blob/main/lib/chronicle/etl/transformers/sampler_transformer.rb) - sort extracted results by `key` and `direction`
+
 
 #### Loaders
 
-- [`table`](https://github.com/chronicle-app/chronicle-etl/blob/main/lib/chronicle/etl/loaders/table_loader.rb) - (default) Output an ascii table of records. Useful for exploring data.
+- [`json`](https://github.com/chronicle-app/chronicle-etl/blob/main/lib/chronicle/etl/loaders/json_loader.rb) - (default) Load records serialized as JSON
+- [`table`](https://github.com/chronicle-app/chronicle-etl/blob/main/lib/chronicle/etl/loaders/table_loader.rb) - Output an ascii table of records. Useful for exploring data.
 - [`csv`](https://github.com/chronicle-app/chronicle-etl/blob/main/lib/chronicle/etl/extractors/csv_extractor.rb) - Load records to CSV
-- [`json`](https://github.com/chronicle-app/chronicle-etl/blob/main/lib/chronicle/etl/loaders/json_loader.rb) - Load records serialized as JSON
-- [`rest`](https://github.com/chronicle-app/chronicle-etl/blob/main/lib/chronicle/etl/loaders/rest_loader.rb) - Serialize records with [JSONAPI](https://jsonapi.org/) and send to a REST API
+- [`rest`](https://github.com/chronicle-app/chronicle-etl/blob/main/lib/chronicle/etl/loaders/rest_loader.rb) - Send JSON to a REST API
 
 ### Chronicle Plugins for third-party services
 
@@ -161,8 +168,8 @@ $ chronicle-etl plugins:list
 $ chronicle-etl plugins:install NAME
 
 # Use a plugin
-$ chronicle-etl plugins:install shell
-$ chronicle-etl --extractor shell:history --limit 10
+$ chronicle-etl plugins:install imessage
+$ chronicle-etl --extractor imessage --limit 10
 
 # Uninstall a plugin
 $ chronicle-etl plugins:uninstall NAME
@@ -219,28 +226,7 @@ If you want to work together on a connector, please [get in touch](#get-in-touch
 #### Sample custom Extractor class
 
 ```ruby
-module Chronicle
-  module FooService
-    class FooExtractor < Chronicle::ETL::Extractor
-      register_connector do |r|
-        r.identifier = 'foo'
-        r.description = 'from foo.com'
-      end
-
-      setting :access_token, required: true
-
-      def prepare
-        @records = # load from somewhere
-      end
-
-      def extract
-        @records.each do |record|
-          yield Chronicle::ETL::Extraction.new(data: row.to_h)
-        end
-      end
-    end
-  end
-end
+# TODO
 ```
 
 ## Secrets Management

Rakefile

@@ -1,5 +1,5 @@
-require "bundler/gem_tasks"
-require "rspec/core/rake_task"
+require 'bundler/gem_tasks'
+require 'rspec/core/rake_task'
 RSpec::Core::RakeTask.new(:spec)
 
 require 'yard'

bin/console

@@ -1,26 +1,25 @@
 #!/usr/bin/env ruby
 
-require "bundler/setup"
-require "chronicle/etl"
+require 'bundler/setup'
+require 'chronicle/etl'
 
 # You can add fixtures and/or initialization code here to make experimenting
 # with your gem easier. You can also use a different console, if you like.
 
 # (If you use this, don't forget to add pry to your Gemfile!)
-require "pry"
+require 'pry'
 Pry.start
 
 def reload!(print = true)
   puts 'Reloading ...' if print
   # Main project directory.
   root_dir = File.expand_path('..', __dir__)
   # Directories within the project that should be reloaded.
-  reload_dirs = %w{lib}
+  reload_dirs = %w[lib]
   # Loop through and reload every file in all relevant project directories.
   reload_dirs.each do |dir|
     Dir.glob("#{root_dir}/#{dir}/**/*.rb").each { |f| load(f) }
   end
   # Return true when complete.
   true
 end
-

chronicle-etl.gemspec

@@ -1,73 +1,73 @@
+# frozen_string_literal: true
 
-lib = File.expand_path("../lib", __FILE__)
+lib = File.expand_path('lib', __dir__)
 $LOAD_PATH.unshift(lib) unless $LOAD_PATH.include?(lib)
-require "chronicle/etl/version"
+require 'chronicle/etl/version'
 
 Gem::Specification.new do |spec|
-  spec.name          = "chronicle-etl"
+  spec.name          = 'chronicle-etl'
   spec.version       = Chronicle::ETL::VERSION
-  spec.authors       = ["Andrew Louis"]
-  spec.email         = ["[email protected]"]
+  spec.authors       = ['Andrew Louis']
+  spec.email         = ['[email protected]']
 
-  spec.summary       = "ETL tool for personal data"
-  spec.description   = "Chronicle-ETL allows you to extract personal data from a variety of services, transformer it, and load it."
-  spec.homepage      = "https://github.com/chronicle-app"
-  spec.license       = "MIT"
+  spec.summary       = 'ETL tool for personal data'
+  spec.description   = 'Chronicle-ETL allows you to extract personal data from a variety of services, transformer it, and load it.'
+  spec.homepage      = 'https://github.com/chronicle-app'
+  spec.license       = 'MIT'
 
   # Prevent pushing this gem to RubyGems.org. To allow pushes either set the 'allowed_push_host'
   # to allow pushing to a single host or delete this section to allow pushing to any host.
   if spec.respond_to?(:metadata)
-    spec.metadata['allowed_push_host'] = "https://rubygems.org"
+    spec.metadata['allowed_push_host'] = 'https://rubygems.org'
 
-    spec.metadata["homepage_uri"] = spec.homepage
-    spec.metadata["source_code_uri"] = "https://github.com/chronicle-app/chronicle-etl"
-    spec.metadata["changelog_uri"] = "https://github.com/chronicle-app/chronicle-etl/releases"
+    spec.metadata['homepage_uri'] = spec.homepage
+    spec.metadata['source_code_uri'] = 'https://github.com/chronicle-app/chronicle-etl'
+    spec.metadata['changelog_uri'] = 'https://github.com/chronicle-app/chronicle-etl/releases'
   else
-    raise "RubyGems 2.0 or newer is required to protect against " \
-      "public gem pushes."
+    raise 'RubyGems 2.0 or newer is required to protect against ' \
+          'public gem pushes.'
   end
 
   # Specify which files should be added to the gem when it is released.
   # The `git ls-files -z` loads the files in the RubyGem that have been added into git.
-  spec.files         = Dir.chdir(File.expand_path('..', __FILE__)) do
+  spec.files = Dir.chdir(File.expand_path(__dir__)) do
     `git ls-files -z`.split("\x0").reject { |f| f.match(%r{^(test|spec|features)/}) }
   end
-  spec.bindir        = "exe"
+  spec.bindir        = 'exe'
   spec.executables   = spec.files.grep(%r{^exe/}) { |f| File.basename(f) }
-  spec.require_paths = ["lib"]
-  spec.required_ruby_version = ">= 2.7"
+  spec.require_paths = ['lib']
+  spec.required_ruby_version = '>= 3.1'
+  spec.metadata['rubygems_mfa_required'] = 'true'
 
-  spec.add_dependency "activesupport", "~> 7.0"
-  spec.add_dependency "chronicle-core", "~> 0.2.2"
-  spec.add_dependency "chronic_duration", "~> 0.10.6"
-  spec.add_dependency "colorize", "~> 0.8.1"
-  spec.add_dependency "gems", ">= 1"
-  spec.add_dependency "launchy"
-  spec.add_dependency "marcel", "~> 1.0.2"
-  spec.add_dependency "mini_exiftool", "~> 2.10"
-  spec.add_dependency "nokogiri", "~> 1.13"
-  spec.add_dependency "omniauth", "~> 2"
-  spec.add_dependency "sequel", "~> 5.35"
-  spec.add_dependency "sinatra", "~> 2"
-  spec.add_dependency "sqlite3", "~> 1.4"
-  spec.add_dependency "thor", "~> 1.2"
-  spec.add_dependency "thor-hollaback", "~> 0.2"
-  spec.add_dependency "tty-progressbar", "~> 0.17"
-  spec.add_dependency "tty-prompt", "~> 0.23"
-  spec.add_dependency "tty-spinner"
-  spec.add_dependency "tty-table", "~> 0.11"
-  spec.add_dependency "xdg", ">= 4.0"
+  spec.add_dependency 'activesupport', '~> 7.0'
+  spec.add_dependency 'chronic_duration', '~> 0.10.6'
+  spec.add_dependency 'chronicle-core', '~> 0.3'
+  spec.add_dependency 'colorize', '~> 0.8.1'
+  spec.add_dependency 'gems', '>= 1'
+  spec.add_dependency 'launchy'
+  spec.add_dependency 'marcel', '~> 1.0.2'
+  spec.add_dependency 'omniauth', '~> 2'
+  spec.add_dependency 'sequel', '~> 5.35'
+  spec.add_dependency 'sinatra', '~> 2'
+  spec.add_dependency 'sqlite3', '~> 1.4'
+  spec.add_dependency 'thor', '~> 1.2'
+  spec.add_dependency 'thor-hollaback', '~> 0.2'
+  spec.add_dependency 'tty-progressbar', '~> 0.17'
+  spec.add_dependency 'tty-prompt', '~> 0.23'
+  spec.add_dependency 'tty-spinner'
+  spec.add_dependency 'tty-table', '~> 0.12'
+  spec.add_dependency 'xdg', '>= 4.0'
 
-  spec.add_development_dependency "bundler", "~> 2.1"
-  spec.add_development_dependency "fakefs", "~> 1.4"
-  spec.add_development_dependency "guard-rspec", "~> 4.7.3"
-  spec.add_development_dependency "pry-byebug", "~> 3.9"
-  spec.add_development_dependency "rake", "~> 13.0"
-  spec.add_development_dependency "rspec", "~> 3.9"
-  spec.add_development_dependency "rubocop", "~> 1.25.1"
-  spec.add_development_dependency "simplecov", "~> 0.21"
-  spec.add_development_dependency "vcr", "~> 6.1"
-  spec.add_development_dependency "webmock", "~> 3"
-  spec.add_development_dependency "webrick", "~> 1.7"
-  spec.add_development_dependency "yard", "~> 0.9.7"
+  spec.add_development_dependency 'bundler', '~> 2.1'
+  spec.add_development_dependency 'fakefs', '~> 1.4'
+  spec.add_development_dependency 'guard-rspec', '~> 4.7.3'
+  spec.add_development_dependency 'pry-byebug', '~> 3.9'
+  spec.add_development_dependency 'rake', '~> 13.0'
+  spec.add_development_dependency 'rspec', '~> 3.9'
+  spec.add_development_dependency 'rubocop', '~> 1.57'
+  spec.add_development_dependency 'simplecov', '~> 0.21'
+  spec.add_development_dependency 'vcr', '~> 6.1'
+  spec.add_development_dependency 'webmock', '~> 3'
+  spec.add_development_dependency 'webrick', '~> 1.7'
+  spec.add_development_dependency 'yard', '~> 0.9.7'
 end

exe/chronicle-etl

@@ -1,5 +1,5 @@
 #!/usr/bin/env ruby
 
-require "chronicle/etl/cli"
+require 'chronicle/etl/cli'
 
 Chronicle::ETL::CLI::Main.start(ARGV)

lib/chronicle/etl.rb

@@ -1,11 +1,15 @@
+# frozen_string_literal: true
+
 require 'chronicle/schema'
+require 'chronicle/models/base'
 
 require_relative 'etl/registry/registry'
 require_relative 'etl/authorizer'
 require_relative 'etl/config'
 require_relative 'etl/configurable'
 require_relative 'etl/exceptions'
 require_relative 'etl/extraction'
+require_relative 'etl/record'
 require_relative 'etl/job_definition'
 require_relative 'etl/job_log'
 require_relative 'etl/job_logger'
@@ -14,7 +18,6 @@
 require_relative 'etl/runner'
 require_relative 'etl/secrets'
 require_relative 'etl/utils/binary_attachments'
-require_relative 'etl/utils/text_recognition'
 require_relative 'etl/utils/progress_bar'
 require_relative 'etl/version'